From: Stefan Hajnoczi <stefanha@redhat.com>
To: qemu-devel@nongnu.org
Cc: Gabriel Kerneis <gabriel@kerneis.info>,
Stefan Hajnoczi <stefanha@redhat.com>,
Anthony Liguori <anthony@codemonkey.ws>
Subject: [Qemu-devel] [PULL 07/11] coroutine: fix /perf/nesting coroutine benchmark
Date: Fri, 20 Sep 2013 19:42:07 +0200 [thread overview]
Message-ID: <1379698931-946-8-git-send-email-stefanha@redhat.com> (raw)
In-Reply-To: <1379698931-946-1-git-send-email-stefanha@redhat.com>
From: Gabriel Kerneis <gabriel@kerneis.info>
The /perf/nesting benchmark is broken because the counters are
not reset after each iteration. Therefore, nesting is done only
on the first iteration, and skipped on every other.
This patch fixes the issue, and reduces the number of iterations
to make it possible to run the benchmark in a reasonable amount of
time.
Signed-off-by: Gabriel Kerneis <gabriel@kerneis.info>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
tests/test-coroutine.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/tests/test-coroutine.c b/tests/test-coroutine.c
index 2792191..15a885e 100644
--- a/tests/test-coroutine.c
+++ b/tests/test-coroutine.c
@@ -182,17 +182,17 @@ static void perf_nesting(void)
unsigned int i, maxcycles, maxnesting;
double duration;
- maxcycles = 100000000;
+ maxcycles = 10000;
maxnesting = 1000;
Coroutine *root;
- NestData nd = {
- .n_enter = 0,
- .n_return = 0,
- .max = maxnesting,
- };
g_test_timer_start();
for (i = 0; i < maxcycles; i++) {
+ NestData nd = {
+ .n_enter = 0,
+ .n_return = 0,
+ .max = maxnesting,
+ };
root = qemu_coroutine_create(nest);
qemu_coroutine_enter(root, &nd);
}
--
1.8.3.1
next prev parent reply other threads:[~2013-09-20 17:42 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-09-20 17:42 [Qemu-devel] [PULL 00/11] Block patches Stefan Hajnoczi
2013-09-20 17:42 ` [Qemu-devel] [PULL 01/11] libcacard: link against qemu-error.o for error_report() Stefan Hajnoczi
2013-09-20 17:42 ` [Qemu-devel] [PULL 02/11] osdep: warn if open(O_DIRECT) on fails with EINVAL Stefan Hajnoczi
2013-09-20 17:42 ` [Qemu-devel] [PULL 03/11] qemu-timer: drop outdated signal safety comments Stefan Hajnoczi
2013-09-20 17:42 ` [Qemu-devel] [PULL 04/11] qemu-timer: make qemu_timer_mod_ns() and qemu_timer_del() thread-safe Stefan Hajnoczi
2013-09-20 17:42 ` [Qemu-devel] [PULL 05/11] qemu-timer: do not take the lock in timer_pending Stefan Hajnoczi
2013-09-20 17:42 ` [Qemu-devel] [PULL 06/11] coroutine: add qemu_coroutine_yield benchmark Stefan Hajnoczi
2013-09-20 17:42 ` Stefan Hajnoczi [this message]
2013-09-20 17:42 ` [Qemu-devel] [PULL 08/11] qcow2: Correct snapshots size for overlap check Stefan Hajnoczi
2013-09-20 17:42 ` [Qemu-devel] [PULL 09/11] block: don't lose data from last incomplete sector Stefan Hajnoczi
2013-09-20 17:42 ` [Qemu-devel] [PULL 10/11] blockdev: do not default cache.no-flush to true Stefan Hajnoczi
2013-09-20 17:42 ` [Qemu-devel] [PULL 11/11] virtio-blk: do not relay a previous driver's WCE configuration to the current Stefan Hajnoczi
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1379698931-946-8-git-send-email-stefanha@redhat.com \
--to=stefanha@redhat.com \
--cc=anthony@codemonkey.ws \
--cc=gabriel@kerneis.info \
--cc=qemu-devel@nongnu.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).